aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-04-03 16:21:21 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2014-04-03 16:21:21 +0200
commit9271bc835546a8bd11c645018e9daabd54522855 (patch)
tree033032c696aca96b210205e44e76c56bc557477e /youtube_dl/extractor
parent968ed2a7779fc7337fdcaa12da2b12e288e7eeb6 (diff)
[cnet] Add new extractor (Fixes #2679)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/cnet.py70
2 files changed, 71 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 7c3587e47..c9c400b61 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -40,6 +40,7 @@ from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
from .cmt import CMTIE
+from .cnet import CNETIE
from .cnn import (
CNNIE,
CNNBlogsIE,
diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py
new file mode 100644
index 000000000..6a2f5ce36
--- /dev/null
+++ b/youtube_dl/extractor/cnet.py
@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+)
+
+
+class CNETIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
+ _TEST = {
+ 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
+ 'md5': '041233212a0d06b179c87cbcca1577b8',
+ 'info_dict': {
+ 'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
+ 'ext': 'mp4',
+ 'title': 'Hands-on with Microsoft Windows 8.1 Update',
+ 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
+ 'thumbnail': 're:^http://.*/flmswindows8.jpg$',
+ 'uploader_id': 'sarah.mitroff@cbsinteractive.com',
+ 'uploader': 'Sarah Mitroff',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ display_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, display_id)
+ data_json = self._html_search_regex(
+ r"<div class=\"cnetVideoPlayer\" data-cnet-video-options='([^']+)'",
+ webpage, 'data json')
+ data = json.loads(data_json)
+ vdata = data['video']
+
+ video_id = vdata['id']
+ title = vdata['headline']
+ description = vdata.get('dek')
+ thumbnail = vdata.get('image', {}).get('path')
+ author = vdata.get('author')
+ if author:
+ uploader = '%s %s' % (author['firstName'], author['lastName'])
+ uploader_id = author.get('email')
+ else:
+ uploader = None
+ uploader_id = None
+
+ formats = [{
+ 'format_id': '%s-%s-%s' % (
+ f['type'], f['format'],
+ int_or_none(f.get('bitrate'), 1000, default='')),
+ 'url': f['uri'],
+ 'tbr': int_or_none(f.get('bitrate'), 1000),
+ } for f in vdata['files']['data']]
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'formats': formats,
+ 'description': description,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'thumbnail': thumbnail,
+ }